LLM Mart Basic

用于强化章节结尾的章末钩子。适合章末抢救、结尾补针、翻页感增强、下一章驱动增强与最后 150–300 字局部强化。关键词：强化章末钩子、结尾没翻页感、只修结尾、下一章驱动、最后一句、章末补针。

用于强化章节开头前 150–300 字的入场抓力。适合章首抢救、首屏留存优化、异常前置、冲突前置与只修前两三段的局部强化。关键词：强化开头、章首抓人、前 150–300 字、首屏留存、开头太慢、只修前两段。

用于设计或重写场景单元、章节场景与微型剧本。适合场景施工卡落地、动作链推进、证据入场、对话承压与控制卡到场景的职责拆解。关键词：场景单元、场景施工卡、微型剧本、动作链、证据推进、场景职责。

用于设计、重写或强化对话冲突。适合把角色对话写成立场碰撞、潜台词拉扯、信息释放与情绪升级并存的有效场景。关键词：对话冲突、盘问、谈判、争执、潜台词、关系升级。

执行微空间或受限空间场景。用于在楼道、电梯、值班室、走廊、地下车库、出租屋、候诊区、办公室后区等熟悉空间里，把空间常态、微反常、人物动作、后果升级与证据入场咬成一个可落地的场景引擎；执行时必须先加载 通用-执行场景单元，再叠加本 Skill 的微空间专项工法。适合微空间惊悚、受限场景压迫、日常异化场景设计。

提纯多平台输出前的中文母稿。用于在不同平台改写前，把正文母稿修成信息稳、事件链稳、情绪主轴清、证据与规则关键点不丢、追读链完整、平台可分化的高质量源稿，避免后续平台适配建立在松散底稿上。适合多平台前置精修、母稿加固、跨平台源稿提纯。

用于撰写、重写或审计小说书评。适合把全书 / 分部 / 分卷 / 分章的阅读体验、核心卖点、平台传播口径与非剧透钩子写成可直接发布的书评文件。关键词：撰写书评、推荐文案、分章安利、平台推荐评述、非剧透书评、今日头条。

用于撰写、重写或审计作品的内容简介。简介即开篇——读者看简介的决策模式与看开头完全一致：在 3–5 秒内决定要不要点开。适合把题材卖点、主角处境、核心冲突、持续承诺与情绪抓手压缩成平台可用文本，支持全层级（全书/分部/分卷/章节）简介。关键词：内容简介、作品简介、平台简介、卖点压缩、简介重写、简介审计、简介同构。

用于润色已有章节正文。适合整章精修、局部重写、节奏提纯、章首抓力增强、中段回报提亮与章末钩子收紧。关键词：润这章、精修正文、整章精修、局部重写、节奏提纯、直接回写。

润色章节后的 `## 作者有话说`。用于把作者有话说修成读者向小剧场：一丢丢创作花絮 + 一点贴着本章余波的情绪共鸣 + 一个开放式轻追问，而不是创作说明会、设定讲义或章节总结。适合发布前精修、后记前小剧场重写、把作者有话说从复盘腔改回读者腔。

专用于小说写作的结构化深度研究 Skill。支持对题材趋势、平台生态、专业知识、场景环境、人物原型、写作技法、读者市场等研究域，执行大纲生成→并行深搜→报告输出的全流程深度调研。关键词：深度研究、写作研究、题材调研。

用于生成写前章节控制卡、章节施工卡或章节作战卡。适合写前施工、场景拆分、中段回报预埋、章末钩子预埋与上游供血对齐。关键词：章节控制卡、施工卡、作战卡、中段回报、章末钩子、写前施工。

用于对单章或连续多章执行"初始化→控制卡→创作→润色→去AI味→审阅回炉→读者产物→摘要"的完整章节闭环。适合章节写作 SOP、批量写章、日志续跑、9.2+ 回炉与最终摘要收口。关键词：章节创作闭环、跑完整 SOP、批量写章、回炉到 9.2、日志续跑、最终摘要。

用于管理章节与卷层的连续性、冷热线、动态状态与回归压力。适合写前判断该回什么、写后更新动态状态、检查中段失温与追踪章节链路热度。关键词：连续性、冷热线、谁该回来了、哪些线快忘了、动态状态、失温检查。

用于蒸馏一部成功小说的叙事架构 DNA、故事线台账、套路指纹与读者吸引留存策略，产出可被下游写/审/改 Skill 消费的"作品蓝本模板"。蒸馏优先级：书名策略 > 内容简介 > 黄金三章 > 章标题/章首/章末模式 > 套路配置 > 故事线台账。适合把一部作品的"读者为何点开/为何追读"的核心回路提炼为可参照的结构约束。关键词：蒸馏作品蓝本、叙事架构DNA、故事线台账、读者吸引指纹、黄金三章拆解、书名策略、套路指纹、章标题策略、钩子指纹、交叉蒸馏。

用于蒸馏一位小说作者的文笔 DNA，产出可被下游写/审/改 Skill 消费的"作者风格模板"。适合把作者的多部作品的文笔特征提炼为可测量的风格约束（句长基线、段落节奏、感官偏好、对话标签偏好、比喻指纹、禁忌清单），并在目标项目根目录自动注册到 Agents.md。关键词：蒸馏作者文风、作者风格模板、文笔DNA、风格注入、文风复刻。

用于从写作研究报告（题材×平台级）中提取可执行写作约束，产出"写作研究模板"，作为下游写/审/改 Skill 的题材×平台默认约束基线。蒸馏源默认扫描小说项目根"写作研究/"目录 + "调研报告/"目录 + "CommonSkills/写作研究/"目录；支持指定目录、文件、URL 或 网络搜索内容。关键词：蒸馏写作研究、研究报告提取、题材平台约束、写作约束基线、规则提取。

用于在已有素材库目录（默认：项目根/素材库/）中定向补充、扩写或新建素材条目。适合素材库缺件诊断、定向搜索补充、按格式落盘、同步更新总索引与搜索日志的全流程闭环操作。关键词：补充素材、素材库缺件、素材收集、桥段池补全、人物设定填充、名场面扩写、搜索补素材、素材格式标准化。

用于设计单元案、案件母板或事件引擎。适合把局部事件做成可供章节拆分、主线供血、规则显影、人物代价与案件余波同时成立的结构骨架。这里的“主线供血”默认指：推进主线关键问题、补入可回收拼图或抬升核心冲突压力。关键词：事件案件引擎、单元案、证据链、嫌疑池、案件余波、主线供血。

用于设计、重写、补强人物传记。适合产出可回指、可核查、可直接调用的人物裁判源，并统一承接传记模板、动机代价、能力边界、关系网、成长时间线、价值观与心理弧线。内置 Nuwa 深度人物心智模型注入（心智模型提炼、表达DNA、决策启发式、矛盾张力、诚实边界）。关键词：设计人物传记、人物裁判源、成长时间线、价值观、关系网、心理弧线、心智模型、表达DNA、决策启发式。

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

Analyze git diffs or staged changes and generate conventional commit messages that explain WHY a change was made. Supports auto-detecting type and scope, intelligent file staging, and interactive overrides. Use when asked to "write a commit message", "generate a commit", "describe my changes", "commit this", "summarize my diff", or "/commit".

SOC 2 compliance for Terraform — gap analysis, control implementation, evidence collection, and remediation guidance mapped to SOC 2 Trust Services Criteria.

Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.

Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitors, Dashboards, SLOs, Synthetic tests, and live incident investigation using the Datadog MCP server. Covers Terraform-managed Datadog resources.

Structured platform troubleshooting — classifies the problem layer, collects evidence, forms a root-cause hypothesis, and proposes a fix with validation and rollback steps.

Generate, format, and validate code documentation — docstrings, JSDoc, OpenAPI/Swagger specs, documentation sites, and developer guides.

Measure, benchmark, instrument, and debug DORA metrics (Deployment Frequency, Lead Time for Changes, Change Failure Rate, MTTR) for production engineering teams. Covers GitHub Actions instrumentation, Prometheus recording rules, Grafana dashboards, incident source integration, SaaS tool selection, and anti-pattern detection. Use when asked to "instrument DORA metrics", "benchmark our deployment frequency", "why is my MTTR data missing", or "generate a DORA dashboard".

Deploy and configure Dynatrace — OneAgent Kubernetes Operator, code-level instrumentation, Log Monitoring, custom metrics, SLOs, Dashboards, anomaly detection, Davis AI, and live incident investigation using the Dynatrace MCP server. Covers Terraform-managed Dynatrace resources.

FluxCD entry point — routes to the right workflow based on what you need. Live cluster issue → structured 5-workflow debug trace. Repo health check → 6-phase audit (discovery, validation, API compliance, best practices, security). Helm chart review → helmchart. Starts by asking one question to confirm the right mode.

Design, review, secure, and debug GitHub Actions workflows — reusable workflows, OIDC federation, SHA pinning, token scoping, promotion orchestration, and CI failure diagnosis.

Flux CD and Argo CD — two modes. debug: five structured debug workflows for live clusters (installation, source, HelmRelease, Kustomization, ResourceSet) producing a five-section report. audit: six-phase read-only repo analysis (discovery, validation, API compliance, best practices, security) producing a prioritised Critical/Warning/Info report.

Scaffold, lint, review, security-audit, test, and upgrade-verify Helm charts. Runs an interactive interview to build production-ready charts from scratch. Covers chart structure, values design, schema validation, kubeconform, helm diff, and multi-environment scaffolding. Use when asked to "create a helm chart", "lint my chart", "review my helm chart", "check helm security", "generate values schema", "run helm diff", or "add helm tests".

Design, install, debug, review, plan capacity, audit scaling history, migrate from Cluster Autoscaler, and upgrade Karpenter v1.x on EKS. Covers NodePool, EC2NodeClass, NodeClaim, Spot diversity, disruption strategy, Pod Identity/IRSA, interruption queue, private clusters, AMI rotation, and GitOps integration. Use when asked to "set up Karpenter", "debug why nodes aren't provisioning", "review my NodePool", "what would Karpenter provision for this workload", "why did this node terminate", "migrate from CA", or "upgrade Karpenter".

Design, debug, and review KEDA ScaledObject/ScaledJob autoscaling. Covers all major scalers (Prometheus, SQS, Kafka, Redis, Cron, HTTP Add-on, Azure Service Bus), TriggerAuthentication, scaling lifecycle tuning, GitOps integration, and troubleshooting. Use when asked to "add KEDA autoscaling", "debug why my ScaledObject isn't scaling", "review my KEDA config", or "generate a ScaledObject for <trigger>".

Find, live-validate, map the blast radius of, and revoke leaked secrets with Kingfisher (MongoDB) — across a local repo, Git history, a GitHub/GitLab/Bitbucket org, S3/GCS, Docker images, Slack, Jira, Confluence, Teams, or Postman. Covers local CLI scanning, direct validate/revoke without a scan, baseline management (track only new secrets), kingfisher.yaml policy, CI diff-scan gates, and pre-commit/Husky hooks. Use when asked to "scan for secrets", "is this key still live", "what can this credential reach", "revoke this token", "did we leak a secret", or "block new secrets in CI". Pattern-only secret scan bundled with a CVE pass → /platform-skills:trivy. Secrets-context safety in workflow YAML → /platform-skills:zizmor. Storing/rotating secrets inside the cluster → /platform-skills:secrets.

Cluster baseline scaffolding, RBAC diagnosis and generation, workload hardening, and structured pod/scheduling debug for plain Kubernetes across all distributions.

Generate, test, audit, debug, and migrate Kyverno policies using the new CEL-based policy types (ValidatingPolicy, MutatingPolicy, GeneratingPolicy, ImageValidatingPolicy — all apiVersion policies.kyverno.io/v1). Covers matchConstraints, matchConditions, CEL validations/mutations, generator.Apply(), Audit→Deny promotion, PolicyException, kyverno-cli testing, and migration from legacy ClusterPolicy or PodSecurityPolicy. Use when asked to "write a Kyverno policy", "test a ValidatingPolicy", "audit my cluster for violations", "why is my policy not firing", or "migrate from ClusterPolicy".

Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.

Linux administration and networking diagnostics — DNS, load balancing, VPCs, kernel tuning, and connectivity troubleshooting.

MCP server and client development — scaffold, implement tools/resources/prompts, validate schemas, debug protocol compliance, and deploy with auth and rate limiting.

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with NVIDIA Nemotron, pays…

DSH 插件 · 注入式优化器 0.8（主线）：你照常说话，它在你发送后,AI接收前把"这一轮到底要什么"理清楚，再把这份理解交给工作 AI(上下文注入) —— 原话不改写，条条带逐字依据。含控制界面（档位/权限/模型/上下文/只读工具）、拦截浮层（思维层+产出层）与真实 token 用量。可明显提升大多数模型的发挥稳…

Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹

MCP server and CLI tools for web search and crawling, built on SearXNG and Crawl4AI

Delta MCP is a free app that sits between your AI apps and their MCP servers: one program per task instead of one tool call per step, up to 24.1× fewer tokens i…

Ava turns any Android 5+ device into a voice-first Home Assistant kiosk. Native C++ under the hood, so a 10-year-old tablet still listens, talks, and runs the h…

Roblox Studio macOS Window Capture Fix 2026: Real Screenshot Tool Instead of Magenta Playtest Glitch

LabTether